Scribd
Upload
22 views7 pages

Data Screening and Psychometrics

Uploaded by

kainat
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
22 views7 pages

Data Screening and Psychometrics

Uploaded by

kainat
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 7

Data Analysis

Data Screening and Cleaning Steps


The purpose of data screening is to check if data have been entered correctly, such as out-of-
range values. Following steps will be done:
(a) Check for missing values, and deciding how to deal with the missing values.
(b) Check for outliers, and deciding how to deal with outliers.
(c) Check for normality, and deciding how to deal with non-normality.

a) Identifying and dealing with missing Values


 Go to Analyze > Descriptive Statistics > Frequencies
 Select the variables you want to check for missing values and move them to the
‘Variables’ box> Statistics> Mean Click ‘OK’. The output will show the frequency of
missing values for each variable and mean values too.
 If there are missing values, note the mean value of missing entries and round it off to
whole number.
Filling Missing value by Recode into same variables
Click Transform > Recode into same variables > Add items you want to replace > Click ‘Old and
new values > Click ‘system missing’ > Add new value > Click add > Continue > OK
 (Repeat the process again for other items.)
 *To verify do the first step *
Reverse Coding of Questionnaires
1 = 7, 2 = 6, 3 = 5, 4 = 4, 5 = 3, 6 = 2, 7 = 1
* Scoring instructions are given by the author. *
Commands: Transform > recode into same variable > Select only those items which are to be
reverse coded > Click ‘Old and new values’ > add new values reverse coded as given above >
click OK.
b) Identifying and dealing with outliers
An outlier is an observation that lies an abnormal distance from other values in a random sample
from a population. Outliers are generally determined through box plot method in SPSS.

There are two types of outliers: Mild and Extreme Outliers


Mild Outliers – They are represented as mini circles (o). We only identify these outliers and do
not deal with them.
Extreme Outliers – They are represented as star (*). We deal with extreme outliers.
 Analyze > Descriptive Statistics > Explore > Add all the items to variable box
(Dependent List) >Statistics > Statistics > Continous> Click OK.
Dealing with extreme outliers
1. Check participants original responses (Fix it in the data view).
2. Delete that case form the file.
3. Change the score with less extreme score.
Check Reliability of Questionnaire
“Reliability” is how well a test measures what it should. For example, a company might give a
job satisfaction survey to their employees. High reliability means it measures job satisfaction,
while low reliability means it measures something else (or possibly nothing at all).
Internal consistency is typically measured using Cronbach's Alpha (α). Cronbach's Alpha ranges
from 0 to 1, with higher values indicating greater internal consistency (and ultimately reliability).
.00 to .69 = Poor
.70 to .79 = Fair
.80 to .89 = Good
.90 to .99 = Excellent/Strong
SPSS Commands. Analyze > Scale > Reliability Analysis > Select the items of which you want
to check the reliability > Move them to ‘item box’ > Click Statistics > Descriptive (Scale and
Scale if item deleted) >Summaries (Mean) > Continue > OK.
Output. Check value of Cronbach alpha in the ‘Reliability Statistics’ Table. If there is poor
reliability, then consult ‘Item total Statistics’ and ‘Cronbach’s Alpha if item deleted’. (We check
this when the value of Cronbach’s alpha value is less than .70).

How to Calculate Mean of the Scale


SPSS Commands.
Transform > Compute variable > Title in Target Variable > go to Numeric Expression > click () >
enter the items one by one. e.g. (MOG1+ MOG2+ MOG3 + MOG4 + MOG5 + MOG6)/6

Range of scores. X min – X max


We will measure range manually
 Check the Likert scale range. E.g. 1 to 6
 Multiply minimum and maximum range with total number of items.
 E.g. total no. of items = 6
 1×6=6 6 × 6 = 36
 Range = 1-36
c) Check if data is normally distributed
It is one of the basic assumptions of parametric tests (inferential statistics). There are two main
methods of checking normality of the data:
1) Graphical (Subjective)
2) Numerical (Objective)
* Central Limit theorem: In probability theory, the central limit theorem (CLT) states that the
distribution of a sample variable approximates a normal distribution (i.e., a “bell curve”) as the
sample size becomes larger, regardless of the population's actual distribution shape.
1) Graphical method. It has further 2 types:
Histogram and Normality Plot

1. SPSS Commands. Click on Graphs\Legacy Dialogs\Histogram>Move your variable of


interest into the Variable box> Check display normal curve> OK

1) Histogram

2) Q-Q plot Analyze> Descriptive statistics > Q-Q Plot

In order to determine normality graphically, we can use the output of a normal Q-Q Plot. If the data are
normally distributed, the data points will be close to the diagonal line. If the data points stray from the
line in an obvious non-linear fashion, the data are not normally distributed. As we can see from the
normal Q-Q plot below, the data is normally distributed. If you are at all unsure of being able to correctly
interpret the graph
2) Numerical method
SPSS Commands. Analyze > Descriptive Statistics > Explore > Transfer the variable that needs to be
tested for normality into the Dependent List: box by either drag-and-dropping or using the button >
Statistics > Normality Plots > Continue >OK
Interpretation. If the Sig. value of the Shapiro-Wilk Test is greater than 0.05, the data is normal. If it is
below 0.05, the data significantly deviate from a normal distribution.

Skewness and Kurtosis.

SPSS Commands. click the Analyze tab, then click Descriptive Statistics, then click
Descriptives> drag variable in variable box> click option> check the boxes next to Kurtosis and
Skewness> continue> ok

Interpretation. Skewness and kutosis value should within the range. + 1.96 (at alpha 0.05), +
2.58 (at alpha 0.01), and + 3.31 (at alpha 0.001)

In statistics, skewness and kurtosis to measure the shape of a distribution.

Skewness measures the asymmetry of a distribution. This value can be positive or negative.

 A negative skew indicates that the tail is on the left side of the distribution, which extends
towards more negative values.
 A positive skew indicates that the tail is on the right side of the distribution, which
extends towards more positive values.
 A value of zero indicates that there is no skewness in the distribution at all, meaning the
distribution is perfectly symmetrical.
Kurtosis is a measure of whether or not a distribution is heavy-tailed or light-tailed relative to a
normal distribution

 Mesokurtosis: An excess kurtosis of 0. Normal distributions are mesokurtic.


 Platykurtosis: A negative excess kurtosis. Platykurtic distributions are thin-tailed,
meaning that they have few outliers.
 Leptokurtosis: A positive excess kurtosis.

Psychometric Table
You have to find all the values and insert them in the following table
Table 3.1
Psychometric Properties of Study Variables (N = 82)

Variables M SD Rang Cronbach’ Skewnes Kurtosi


e sa s s

XYZ
Graphs

Types of graphs

Use the Graphs\Legacy Dialogs menu to create different types of graphs:

1. Histograms: display the distribution of one continuous variable. They provide


information about the shape of the distribution of scores.
2. Bar graphs: display the number of cases in particular categories, or the score on a
continuous variable for different categories.
3. Line graphs: display mean scores of a continuous variable across different categories.
4. Scatterplots: used to examine the relationship between two continuous variables

Table 2.1

Variables M SD N %

Age 30.56 8.93 ____ ____

Identity

Transmen ____ ____ 33 22

Transwomen ____ ____ 117 78

Living with family

Yes ____ ____ 30 20

No ____ ____ 120 80

Socio-demographic Characteristics of Participants

You might also like